Search

Background : In recent times, digitization is gaining importance in different domains of knowledge such as agriculture, medicine, recommendation platforms, the Internet of Things (IoT), and weather forecasting. In agriculture, crop yield estimation is essential for improving productivity and decision-making processes such as financial market forecasting, and addressing food security issues. The main objective of the article is to predict and improve the accuracy of crop yield forecasting using hybrid machine learning (ML) algorithms. Methods: This article proposes hybrid ML algorithms that use specialized ensembling methods such as stacked generalization, gradient boosting, random forest, and least absolute shrinkage and selection operator (LASSO) regression. Stacked generalization is a new model which learns how to best combine the predictions from two or more models trained on the dataset. To demonstrate the applications of the proposed algorithm, aerial-intel datasets from the github data science repository are used. Results: Based on the experimental results done on the agricultural data, the following observations have been made. The performance of the individual algorithm and hybrid ML algorithms are compared using cross-validation to identify the most promising performers for the agricultural dataset.  The accuracy of random forest regressor, gradient boosted tree regression, and stacked generalization ensemble methods are 87.71%, 86.98%, and 88.89% respectively. Conclusions: The proposed stacked generalization ML algorithm statistically outperforms with an accuracy of 88.89% and hence demonstrates that the proposed approach is an effective algorithm for predicting crop yield. The system also gives fast and accurate responses to the farmers., Competing Interests: No competing interests were disclosed., (Copyright: © 2021 Anbananthen KSM et al.)

This paper shows that the zero flow treatment algorithm and the convergence criteria of EPANET 2.2, the latest version of the EPANET 2 open-source software package, may be responsible for convergence to distinctly inaccurate results in the case of networks with low-resistance pipes. As an alternative, the paper suggests a zero flow treatment method proposed earlier, which is based on the smallness of the flow rather than the flow derivative of the head loss as in EPANET 2.2. To avoid spurious convergence, the EPANET 2.2 convergence criteria may be complemented with a criterion based on the flow residuals of the energy balance equations. The monotony of the head loss vs. flow relationship allows these residuals to be checked for a specified tolerance without solving the energy balance equations for the flow. [ABSTRACT FROM AUTHOR]

In a Wireless Sensor Network (WSN), one of the most important issue is to minimize the energy consumption without losing accuracy during faster data transmission. During information broadcast, message communication is to be sent in an optimized way to increase energy efficiency in the networks. By applying various techniques and methodology in cluster WSN the network lifetime is increased and delay is minimized with the load balanced network. To accomplish load balance, Adelson-Velskii and Landis (AVL) tree rotation clustering algorithm is simulated considering the cluster sensor node. A single large area network is divided into multiple clusters using modified K-means clustering algorithm. Computational complexity is reduced through the construction of Minimum Connected Dominating Set with Multi-hop Information (MCDS-MI) and Bi-Partite Graph (BG) technique. Cluster Head (CH) assortment mechanism is implemented to find maximum cover set count of the sensor nodes. In addition, the enactment of the anticipated design is established through simulations during scalable data transmission in a WSN. Hypothetical investigation and experimental simulations are studied by measuring various performance evaluation metrics namely Virtual Dominators, Size Reduction, Network Lifetime and Residual Energy. The results shows that the proposed MSDS-MI system has maximum reduction in network size of 50%, maximum increase in network lifetime of 60% and saved maximum residual energy consumption of 47.76%. The results are encouraging and our proposed method is found to be more efficient than Connected Dominating Sets (CDS), Pseudo Dominating Sets (PDS), Dynamic Cluster Head Genetic Algorithm (DCH-GA) and Distributed Self-Healing Approach (DSHA). [ABSTRACT FROM AUTHOR]

This paper presents a pioneer study of identifying the wind turbine blade condition based on its vibration pattern. The study used variational mode decomposition (VMD) for signal pre-processing. VMD is an adaptive signal decomposition technique, which can non-recursively decompose a multi-component signal into a number of quasi-orthogonal intrinsic mode functions. This new tool is based on a solid mathematical foundation and can obtain a well-defined time–frequency representation. The main advantage of VMD is, there is no residual noise in the modes and it can avoid redundant modes. Thus, VMD provides a noise-free fault signal for classification. Initially, the obtained vibration data are pre-processed using VMD and then the descriptive statistical features like mean, standard deviation, sample variance, and kurtosis were extracted. After the feature extraction, the dominant features were selected using the C4.5 decision tree algorithm. In this study, multilayer perceptron (MLP) was used for fault classification (blade bend, blade crack, erosion, hub-blade loose connection, and pitch angle twist). Then a comparative study was made with MLP without VMD and MLP with VMD to suggest a better model. From the results, the maximum classification accuracy of 87% was obtained for MLP with VMD when compared to MLP without VMD (76.83%). [ABSTRACT FROM AUTHOR]

In this paper, a fuzzy logic--based jamming detection algorithm (FLJDA) is proposed to detect the presence of jamming in downstream data communication for cluster-based wireless sensor networks. The proposed FLJDA keeps an eye on the existing nodes and new node to determine their behavior by applying fuzzy logic on measured jamming detection metrics. To monitor the behavior of the nodes, the FLJDA computes the jamming detection metrics, namely, packet delivery ratio and received signal strength indicator. The major features of this paper are the following: (1) The jamming detection algorithm is specifically implemented for downstream data communication, (2) cluster head estimates jamming detection metrics for detecting the jamming unlike the existing algorithms where individual nodes explicitly collect the jamming detection metrics, and (3) the proposed algorithm optimizes the jamming detection metrics on the basis of fuzzy logic unlike the existing approaches, which uses merely jamming detection threshold alone for jamming detection. The simulation results of the proposed system provide the true detection ratio as high as 99.89%. [ABSTRACT FROM AUTHOR]

Consider a PRV placed in pipe HT ht to control the pressure at its downstream node. [Extracted from the article]

A new approach is presented for the optimization of steel lattice towers by combining genetic algorithms and an object-oriented approach. The purpose of this approach is to eliminate the difficulties in the handling of large size problems such as lattice towers. Improved search and rapid convergence are obtained by considering the lattice tower as a set of small objects and combining these objects into a system. This is possible with serial cantilever structures such as lattice towers. A tower consists of panel objects, which can be classified as separate objects, as they possess an independent property as well as inherent properties. This can considerably reduce the design space of the problem and enhance the result. An optimization approach for the steel lattice tower problem using objects and genetic algorithms is presented here. The paper also describes the algorithm with practical design considerations used for this approach. To demonstrate the approach, a typical tower configuration with practical constraints has been considered for discrete optimization with the new approach and compared with the results of a normal approach in which the full tower is considered. [ABSTRACT FROM AUTHOR]